"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution

TL;DR

This study analyzes how coding agents perform refactoring during issue resolution, finding they do so less frequently and with less intensity than humans, and proposes a refactoring-aware approach to improve code quality.

Contribution

It provides the first empirical analysis of tangled refactorings in coding agents and introduces a refactoring-aware refinement method to enhance code compilability.

Findings

Coding agents introduce fewer tangled refactorings than humans.

Refactoring-aware approach improves compilability from 19.34% to 38.33%.

Tangled refactorings are linked to reduced compilability but not to correctness.

Abstract

Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which human developers naturally incorporate refactoring as part of the resolution process, resulting in tangled refactoring. Since LLMs are trained on large-scale open-source repositories, coding agents may inherit such behaviors. In this paper, we conduct an empirical study on Multi-SWE-bench, analyzing 3,691 valid patches generated by three agent frameworks with 12 LLMs. We find that coding agents introduce tangled refactorings less frequently (21.43% vs. 36.72%) and with lower intensity (0.66 vs. 1.75) than human developers, although they exhibit a broader diversity of refactoring types. Logistic regression analysis further shows that tangled refactorings are strongly associated with reduced compilability, while exhibiting no significant association with functional correctness. Based on these findings, we propose a refactoring-aware refinement approach that assesses the necessity and safety of tangled refactorings and selectively removes or repairs problematic operations. Our approach improves compilability from 19.34% to 38.33%, and additionally resolves 2.79% previously unresolved issues. Overall, this work presents the first step towards understanding tangled refactoring practices in agentic issue resolution and opens up avenues for future work.